Upload with huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+language: 
+- en
+license: apache-2.0
+---
+
+# BERT multilingual base model (cased)
+
+Pretrained model on the English dataset using a masked language modeling (MLM) objective.
+It was introduced in [this paper](https://arxiv.org/abs/1810.04805) and first released in
+[this repository](https://github.com/google-research/bert). This model is case sensitive: it makes a difference
+between english and English.
+
+## Model description
+
+BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
+it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
+publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
+was pretrained with two objectives:
+
+- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
+  the entire masked sentence through the model and has to predict the masked words. This is different from traditional
+  recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
+  GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
+  sentence.
+- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
+  they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
+  predict if the two sentences were following each other or not.
+
+The pretrained model has been finetuned for one specific language for one specific task. 
+
+### How to use
+
+Here is how to use this model to get the features of a given text in PyTorch:
+
+```python
+from transformers import BertTokenizer, BertModel
+model = BertModel.from_pretrained("mushfiqur11/<repo_name>")
+```

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51d792ad06f5991cf1d0e19ed3865185058d00fd39698f63ffc75a931fece4b
+size 430992429

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.9280742459396751,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-masakhaner-pcm/checkpoint-1000",
+  "epoch": 29.850746268656717,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.99,
+      "eval_accuracy_score": 0.9857660455486542,
+      "eval_f1": 0.9040060468631896,
+      "eval_loss": 0.050759539008140564,
+      "eval_precision": 0.872992700729927,
+      "eval_recall": 0.9373040752351097,
+      "eval_runtime": 4.2853,
+      "eval_samples_per_second": 71.408,
+      "eval_steps_per_second": 9.101,
+      "step": 200
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy_score": 0.9886128364389234,
+      "eval_f1": 0.9248826291079814,
+      "eval_loss": 0.058611851185560226,
+      "eval_precision": 0.9234375,
+      "eval_recall": 0.9263322884012539,
+      "eval_runtime": 4.2846,
+      "eval_samples_per_second": 71.419,
+      "eval_steps_per_second": 9.102,
+      "step": 400
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1357,
+      "step": 500
+    },
+    {
+      "epoch": 8.96,
+      "eval_accuracy_score": 0.9886128364389234,
+      "eval_f1": 0.9205607476635514,
+      "eval_loss": 0.06370853632688522,
+      "eval_precision": 0.9148606811145511,
+      "eval_recall": 0.9263322884012539,
+      "eval_runtime": 4.2868,
+      "eval_samples_per_second": 71.382,
+      "eval_steps_per_second": 9.098,
+      "step": 600
+    },
+    {
+      "epoch": 11.94,
+      "eval_accuracy_score": 0.9877070393374742,
+      "eval_f1": 0.9252336448598131,
+      "eval_loss": 0.07289239019155502,
+      "eval_precision": 0.9195046439628483,
+      "eval_recall": 0.9310344827586207,
+      "eval_runtime": 4.2837,
+      "eval_samples_per_second": 71.433,
+      "eval_steps_per_second": 9.104,
+      "step": 800
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0029,
+      "step": 1000
+    },
+    {
+      "epoch": 14.93,
+      "eval_accuracy_score": 0.9880952380952381,
+      "eval_f1": 0.9280742459396751,
+      "eval_loss": 0.07048221677541733,
+      "eval_precision": 0.916030534351145,
+      "eval_recall": 0.9404388714733543,
+      "eval_runtime": 4.2789,
+      "eval_samples_per_second": 71.514,
+      "eval_steps_per_second": 9.115,
+      "step": 1000
+    },
+    {
+      "epoch": 17.91,
+      "eval_accuracy_score": 0.9858954451345756,
+      "eval_f1": 0.9140201394268009,
+      "eval_loss": 0.08080413192510605,
+      "eval_precision": 0.9035222052067381,
+      "eval_recall": 0.9247648902821317,
+      "eval_runtime": 4.2826,
+      "eval_samples_per_second": 71.452,
+      "eval_steps_per_second": 9.107,
+      "step": 1200
+    },
+    {
+      "epoch": 20.9,
+      "eval_accuracy_score": 0.9879658385093167,
+      "eval_f1": 0.921278254091972,
+      "eval_loss": 0.0840262845158577,
+      "eval_precision": 0.9162790697674419,
+      "eval_recall": 0.9263322884012539,
+      "eval_runtime": 4.2834,
+      "eval_samples_per_second": 71.439,
+      "eval_steps_per_second": 9.105,
+      "step": 1400
+    },
+    {
+      "epoch": 22.39,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0018,
+      "step": 1500
+    },
+    {
+      "epoch": 23.88,
+      "eval_accuracy_score": 0.9855072463768116,
+      "eval_f1": 0.9083969465648855,
+      "eval_loss": 0.09424283355474472,
+      "eval_precision": 0.8854166666666666,
+      "eval_recall": 0.932601880877743,
+      "eval_runtime": 4.2901,
+      "eval_samples_per_second": 71.328,
+      "eval_steps_per_second": 9.091,
+      "step": 1600
+    },
+    {
+      "epoch": 26.87,
+      "eval_accuracy_score": 0.9874482401656315,
+      "eval_f1": 0.9267912772585669,
+      "eval_loss": 0.08567387610673904,
+      "eval_precision": 0.9210526315789473,
+      "eval_recall": 0.932601880877743,
+      "eval_runtime": 4.2857,
+      "eval_samples_per_second": 71.4,
+      "eval_steps_per_second": 9.1,
+      "step": 1800
+    },
+    {
+      "epoch": 29.85,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0019,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "eval_accuracy_score": 0.9856366459627329,
+      "eval_f1": 0.9179566563467493,
+      "eval_loss": 0.09690915793180466,
+      "eval_precision": 0.9067278287461774,
+      "eval_recall": 0.9294670846394985,
+      "eval_runtime": 4.282,
+      "eval_samples_per_second": 71.462,
+      "eval_steps_per_second": 9.108,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "step": 2000,
+      "total_flos": 8286244530923520.0,
+      "train_loss": 0.035582695484161375,
+      "train_runtime": 2228.4914,
+      "train_samples_per_second": 215.392,
+      "train_steps_per_second": 6.731
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 224,
+  "total_flos": 8286244530923520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac01d85f765a077a924ac18ffd14c26b1d698a2fd76cec84313c4044a57f1637
+size 3259